{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O7555Z35KNABD4766UORL64SG7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bd43e284eceb5c3a954068218b13f126598ab343844776db3be0936ee0eb3ac1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-22T05:18:27Z","title_canon_sha256":"3997bc25af811b53fb3d38f0d761dc67a63d51dba4c6a99dee5c640aaa109a4e"},"schema_version":"1.0","source":{"id":"2205.10747","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10747","created_at":"2026-07-05T05:06:11Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10747v4","created_at":"2026-07-05T05:06:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10747","created_at":"2026-07-05T05:06:11Z"},{"alias_kind":"pith_short_12","alias_value":"O7555Z35KNAB","created_at":"2026-07-05T05:06:11Z"},{"alias_kind":"pith_short_16","alias_value":"O7555Z35KNABD476","created_at":"2026-07-05T05:06:11Z"},{"alias_kind":"pith_short_8","alias_value":"O7555Z35","created_at":"2026-07-05T05:06:11Z"}],"graph_snapshots":[{"event_id":"sha256:420ab0abcb94410c6cbb20ed1910d8ac8b1d337c63c5a7981103fd2bd3dd5c6c","target":"graph","created_at":"2026-07-05T05:06:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2205.10747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples, such as domain-specific captioning, question answering, and future event prediction. Existing few-shot video-language learners focus exclusively on the encoder, resulting in the absence of a video-to-text decoder to handle generative tasks. Video captioners have been pretrained on large-scale video-language datasets, but they rely heavily on finetuning and lack the ability to generate text for unseen tasks in a few-shot setting. We propose VidIL, a few-shot Vid","authors_text":"Chenguang Zhu, Derek Hoiem, Heng Ji, Jie Lei, Luowei Zhou, Manling Li, Mohit Bansal, Ruochen Xu, Shih-Fu Chang, Shuohang Wang, Xudong Lin, Zhenhailong Wang, Ziyi Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-22T05:18:27Z","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10747","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a7488ff72e26b6b59979e7e17ced16b49b4507893d91dd5718d880885c3133ad","target":"record","created_at":"2026-07-05T05:06:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bd43e284eceb5c3a954068218b13f126598ab343844776db3be0936ee0eb3ac1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-22T05:18:27Z","title_canon_sha256":"3997bc25af811b53fb3d38f0d761dc67a63d51dba4c6a99dee5c640aaa109a4e"},"schema_version":"1.0","source":{"id":"2205.10747","kind":"arxiv","version":4}},"canonical_sha256":"77fbdee77d534011f3fef51d15fb9237eb25dec875ee9d82b99c3c4144e7f059","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77fbdee77d534011f3fef51d15fb9237eb25dec875ee9d82b99c3c4144e7f059","first_computed_at":"2026-07-05T05:06:11.975040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:11.975040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"izPLQtCarA1t70Ook8H5J2G9cMHC/sfU3KxXV1k1pMtvyjdG+C8DaiKmzizQwkQ5P2hJXaBfRVrEE+AGiTSzAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:11.975519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.10747","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7488ff72e26b6b59979e7e17ced16b49b4507893d91dd5718d880885c3133ad","sha256:420ab0abcb94410c6cbb20ed1910d8ac8b1d337c63c5a7981103fd2bd3dd5c6c"],"state_sha256":"1157f4eb078dacc31e0ce0a7d46514c339410fa8a0bcd060a8c45edc24cfef83"}